all InfoSec news
Rethinking the Reverse-engineering of Trojan Triggers. (arXiv:2210.15127v1 [cs.CR])
Oct. 28, 2022, 1:24 a.m. | Zhenting Wang, Kai Mei, Hailun Ding, Juan Zhai, Shiqing Ma
cs.CR updates on arXiv.org arxiv.org
Deep Neural Networks are vulnerable to Trojan (or backdoor) attacks.
Reverse-engineering methods can reconstruct the trigger and thus identify
affected models. Existing reverse-engineering methods only consider input space
constraints, e.g., trigger size in the input space. Expressly, they assume the
triggers are static patterns in the input space and fail to detect models with
feature space triggers such as image style transformations. We observe that
both input-space and feature-space Trojans are associated with feature space
hyperplanes. Based on this observation, …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Red Team Penetration Tester and Operator, Junior
@ Booz Allen Hamilton | USA, VA, McLean (1500 Tysons McLean Dr)
Director, Security Operations & Risk Management
@ Live Nation Entertainment | Toronto, ON
IT and Security Specialist APAC (F/M/D)
@ Flowdesk | Singapore, Singapore, Singapore
Senior Security Controls Assessor
@ Capgemini | Washington, DC, District of Columbia, United States; McLean, Virginia, United States
GRC Systems Solution Architect
@ Deloitte | Midrand, South Africa
Cybersecurity Subject Matter Expert (SME)
@ SMS Data Products Group, Inc. | Fort Belvoir, VA, United States